The Rally Agent works with what's already in your Rally workspace: your study templates, participant properties, governance rules, incentives, and calendar. The more of this you have in place before you start, the more useful the agent is from your first session. This article covers what to set up.

Rally Agent is enabled per workspace. In an agent-enabled workspace, each person also needs a role with the Access to Rally Agents permission. Free seats can't use the agent (they keep read-only MCP access). Admins can update roles in Settings > Roles.

To open the agent, select Rally Agent in the left sidebar of Rally. It opens in a new tab.

How approvals work

Before the agent changes anything in your workspace (publishing a study, sending recruitment emails, sending an incentive, closing a study, or rescheduling or canceling an interview), it shows you what it plans to do and waits for your approval. Questions and lookups, like checking a study's progress or finding participants, don't need approval.

Reviewing each step lets you see what the agent proposes, build intuition for how it works, and flag anything that doesn't look right. Your feedback on individual decisions helps us improve the agent.

Create study templates

The agent searches your templates and proposes the best match when you ask it to start a study.

Create at least one study template for each type of study you plan to run with the agent (1:1 interview, group interview, survey, or unmoderated test) before your first agent session. Each template should include a descriptive name that signals what the study is ("30-min onboarding exit interview," not "Template A"), the session duration, a default incentive amount, a participant target, any custom fields your team captures, and screener questions if you use them. The agent matches on each template's name and description, so add a short description that says when to use it. Only published templates can be used to create studies.

Populate participant properties

The agent finds participants by turning your request into filters on the properties stored in your participant CRM. If those properties are empty or inconsistently filled in, the agent has nothing to filter on and cannot surface a qualified audience.

Go into your participant CRM and fill in the properties your team actually recruits on. You do not need every field filled for every participant. You need the criteria you filter by most often to be consistently populated across your panel. Common examples: role, seniority, company size, industry, product tier, and region.

Add property descriptions. The agent reads each property's description to understand what it means and when to use it. Navigate to Settings > Properties, select a property to edit it, and fill in the Description field. Rally's built-in properties already have descriptions and can't be edited.

If a property you recruit on does not exist in your workspace yet, create it before you build your first agent-assisted study.

Build saved audience views

The agent can find participants by property criteria on its own, but a saved audience view speeds things up. When you ask the agent to source an audience, a named and filtered view gives it a clear, ready-to-go starting point instead of building from scratch each time.

Save the audience segments you come back to repeatedly. Examples: "Enterprise customers," "Recent onboarding completions," "Active B2B users on the free tier." Each saved view should have a name that tells anyone (including the agent) exactly who is in it without having to open it, and it should be filtered on the participant properties you filled in above.

Configure your governance settings

The agent follows every frequency cap, consent requirement, and permission rule you've set up in Rally. It will not contact a participant more often than your rules allow. It will not skip consent steps you have required.

Before your first agent-driven recruitment run, confirm that:

• Engagement rules are set. These control how often any single participant can be contacted and within what time window. 

• User permissions are current. During EA, access to the Agent is controlled. Make sure the right people on your team are enabled.

Configure your incentives

The agent prepares incentive payouts after a completed session and routes them to you for approval. Without incentives configured in Rally, this will not work.

Before your first agent-assisted study, connect and fund your incentives and confirm the denominations your team uses. When the agent surfaces an incentive for approval, you review it, approve it, and it sends.

Connect your calendar and set availability

Participants book interviews against your connected calendar and availability. If your calendar isn't connected, the agent won't turn on scheduling for a study, so participants would have no way to book. Once interviews are booked, the agent can reschedule or cancel them for you, and it can update your working hours when you ask.

Connect Google Calendar or Outlook in Settings > Connected Accounts, then set your working hours in Settings > Availability. Use overrides to mark out-of-office dates or different hours on specific dates, and keep your working hours current. For more on working hours and overrides, see Availability.

Set a participant target on every study

The agent tracks completed sessions against your participant target and asks you to approve closing the study once the target is met. Without a target, it has no signal for when a study is done.

Every study, whether you build it or the agent does, should have a participant target set before it goes live. Setting a target on your templates covers this automatically. This keeps recruitment from running indefinitely and gives the agent a clear finish line to work toward.